ultralytics 8.1.42__tar.gz → 8.1.44__tar.gz

{ultralytics-8.1.42/ultralytics.egg-info → ultralytics-8.1.44}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ultralytics
-Version: 8.1.42
+Version: 8.1.44
 Summary: Ultralytics YOLOv8 for SOTA object detection, multi-object tracking, instance segmentation, pose estimation and image classification.
 Author: Glenn Jocher, Ayush Chaurasia, Jing Qiu
 Maintainer: Glenn Jocher, Ayush Chaurasia, Jing Qiu

{ultralytics-8.1.42 → ultralytics-8.1.44}/tests/test_engine.py

@@ -2,6 +2,7 @@
 
 import sys
 from unittest import mock
+
 from ultralytics import YOLO
 from ultralytics.cfg import get_cfg
 from ultralytics.engine.exporter import Exporter
@@ -52,7 +53,7 @@ def test_detect():
     pred.add_callback("on_predict_start", test_func)
     assert test_func in pred.callbacks["on_predict_start"], "callback test failed"
     # Confirm there is no issue with sys.argv being empty.
-    with mock.patch.object(sys, 'argv', []):
+    with mock.patch.object(sys, "argv", []):
         result = pred(source=ASSETS, model=f"{MODEL}.pt")
         assert len(result), "predictor test failed"
 

{ultralytics-8.1.42 → ultralytics-8.1.44}/tests/test_integrations.py

@@ -34,6 +34,7 @@ def test_mlflow():
 @pytest.mark.skipif(not check_requirements("mlflow", install=False), reason="mlflow not installed")
 def test_mlflow_keep_run_active():
     import os
+
     import mlflow
 
     """Test training with MLflow tracking enabled."""

{ultralytics-8.1.42 → ultralytics-8.1.44}/tests/test_python.py

@@ -10,7 +10,6 @@ import pytest
 import torch
 import yaml
 from PIL import Image
-from torchvision.transforms import ToTensor
 
 from ultralytics import RTDETR, YOLO
 from ultralytics.cfg import TASK2DATA
@@ -108,20 +107,17 @@ def test_predict_img():
     assert len(model(batch, imgsz=32)) == len(batch)  # multiple sources in a batch
 
     # Test tensor inference
-    im = cv2.imread(str(SOURCE))  # OpenCV
-    t = cv2.resize(im, (32, 32))
-    t = ToTensor()(t)
-    t = torch.stack([t, t, t, t])
-    results = model(t, imgsz=32)
-    assert len(results) == t.shape[0]
-    results = seg_model(t, imgsz=32)
-    assert len(results) == t.shape[0]
-    results = cls_model(t, imgsz=32)
-    assert len(results) == t.shape[0]
-    results = pose_model(t, imgsz=32)
-    assert len(results) == t.shape[0]
-    results = obb_model(t, imgsz=32)
-    assert len(results) == t.shape[0]
+    im = torch.rand((4, 3, 32, 32))  # batch-size 4, FP32 0.0-1.0 RGB order
+    results = model(im, imgsz=32)
+    assert len(results) == im.shape[0]
+    results = seg_model(im, imgsz=32)
+    assert len(results) == im.shape[0]
+    results = cls_model(im, imgsz=32)
+    assert len(results) == im.shape[0]
+    results = pose_model(im, imgsz=32)
+    assert len(results) == im.shape[0]
+    results = obb_model(im, imgsz=32)
+    assert len(results) == im.shape[0]
 
 
 def test_predict_grey_and_4ch():
@@ -518,7 +514,8 @@ def test_utils_files():
 @pytest.mark.slow
 def test_utils_patches_torch_save():
     """Test torch_save backoff when _torch_save throws RuntimeError."""
-    from unittest.mock import patch, MagicMock
+    from unittest.mock import MagicMock, patch
+
     from ultralytics.utils.patches import torch_save
 
     mock = MagicMock(side_effect=RuntimeError)
@@ -592,8 +589,6 @@ def image():
 )
 def test_classify_transforms_train(image, auto_augment, erasing, force_color_jitter):
     """Tests classification transforms during training with various augmentation settings."""
-    import torchvision.transforms as T
-
     from ultralytics.data.augment import classify_augmentations
 
     transform = classify_augmentations(
@@ -610,7 +605,6 @@ def test_classify_transforms_train(image, auto_augment, erasing, force_color_jit
         hsv_v=0.4,
         force_color_jitter=force_color_jitter,
         erasing=erasing,
-        interpolation=T.InterpolationMode.BILINEAR,
     )
 
     transformed_image = transform(Image.fromarray(cv2.cvtColor(image, cv2.COLOR_BGR2RGB)))
@@ -658,9 +652,8 @@ def test_yolo_world():
     from ultralytics.models.yolo.world.train_world import WorldTrainerFromScratch
 
     model = YOLO("yolov8s-worldv2.yaml")  # no YOLOv8n-world model yet
-    data = dict(train=dict(yolo_data=["coco8.yaml"]), val=dict(yolo_data=["coco8.yaml"]))
     model.train(
-        data=data,
+        data={"train": {"yolo_data": ["coco8.yaml"]}, "val": {"yolo_data": ["coco8.yaml"]}},
         epochs=2,
         imgsz=32,
         cache="disk",

{ultralytics-8.1.42 → ultralytics-8.1.44}/ultralytics/__init__.py

@@ -1,15 +1,16 @@
 # Ultralytics YOLO 🚀, AGPL-3.0 license
 
-__version__ = "8.1.42"
+__version__ = "8.1.44"
 
 from ultralytics.data.explorer.explorer import Explorer
 from ultralytics.models import RTDETR, SAM, YOLO, YOLOWorld
 from ultralytics.models.fastsam import FastSAM
 from ultralytics.models.nas import NAS
-from ultralytics.utils import ASSETS, SETTINGS as settings
+from ultralytics.utils import ASSETS, SETTINGS
 from ultralytics.utils.checks import check_yolo as checks
 from ultralytics.utils.downloads import download
 
+settings = SETTINGS
 __all__ = (
     "__version__",
     "ASSETS",

{ultralytics-8.1.42 → ultralytics-8.1.44}/ultralytics/cfg/models/v9/yolov9c-seg.yaml

@@ -35,4 +35,4 @@ head:
   - [[-1, 9], 1, Concat, [1]]  # cat head P5
   - [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]]  # 21 (P5/32-large)
 
-  - [[15, 18, 21], 1, Segment, [nc, 32, 256]] # Segment(P3, P4, P5)
+  - [[15, 18, 21], 1, Segment, [nc, 32, 256]]  # Segment(P3, P4, P5)

{ultralytics-8.1.42 → ultralytics-8.1.44}/ultralytics/cfg/models/v9/yolov9c.yaml

@@ -35,4 +35,4 @@ head:
   - [[-1, 9], 1, Concat, [1]]  # cat head P5
   - [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]]  # 21 (P5/32-large)
 
-  - [[15, 18, 21], 1, Detect, [nc]]  # DDetect(P3, P4, P5)
+  - [[15, 18, 21], 1, Detect, [nc]]  # Detect(P3, P4, P5)

{ultralytics-8.1.42 → ultralytics-8.1.44}/ultralytics/cfg/models/v9/yolov9e-seg.yaml

@@ -17,13 +17,13 @@ backbone:
   - [-1, 1, RepNCSPELAN4, [1024, 512, 256, 2]]  # 7
   - [-1, 1, ADown, [1024]]  # 8-P5/32
   - [-1, 1, RepNCSPELAN4, [1024, 512, 256, 2]]  # 9
-   
+
   - [1, 1, CBLinear, [[64]]] # 10
   - [3, 1, CBLinear, [[64, 128]]] # 11
   - [5, 1, CBLinear, [[64, 128, 256]]] # 12
   - [7, 1, CBLinear, [[64, 128, 256, 512]]] # 13
   - [9, 1, CBLinear, [[64, 128, 256, 512, 1024]]] # 14
-  
+
   - [0, 1, Conv, [64, 3, 2]]  # 15-P1/2
   - [[10, 11, 12, 13, 14, -1], 1, CBFuse, [[0, 0, 0, 0, 0]]] # 16
   - [-1, 1, Conv, [128, 3, 2]]  # 17-P2/4
@@ -58,5 +58,4 @@ head:
   - [[-1, 29], 1, Concat, [1]]  # cat head P5
   - [-1, 1, RepNCSPELAN4, [512, 1024, 512, 2]]  # 41 (P5/32-large)
 
-   # segment
   - [[35, 38, 41], 1, Segment, [nc, 32, 256]]  # Segment (P3, P4, P5)

{ultralytics-8.1.42 → ultralytics-8.1.44}/ultralytics/cfg/models/v9/yolov9e.yaml

@@ -17,13 +17,13 @@ backbone:
   - [-1, 1, RepNCSPELAN4, [1024, 512, 256, 2]]  # 7
   - [-1, 1, ADown, [1024]]  # 8-P5/32
   - [-1, 1, RepNCSPELAN4, [1024, 512, 256, 2]]  # 9
-   
+
   - [1, 1, CBLinear, [[64]]] # 10
   - [3, 1, CBLinear, [[64, 128]]] # 11
   - [5, 1, CBLinear, [[64, 128, 256]]] # 12
   - [7, 1, CBLinear, [[64, 128, 256, 512]]] # 13
   - [9, 1, CBLinear, [[64, 128, 256, 512, 1024]]] # 14
-  
+
   - [0, 1, Conv, [64, 3, 2]]  # 15-P1/2
   - [[10, 11, 12, 13, 14, -1], 1, CBFuse, [[0, 0, 0, 0, 0]]] # 16
   - [-1, 1, Conv, [128, 3, 2]]  # 17-P2/4
@@ -58,5 +58,4 @@ head:
   - [[-1, 29], 1, Concat, [1]]  # cat head P5
   - [-1, 1, RepNCSPELAN4, [512, 1024, 512, 2]]  # 41 (P5/32-large)
 
-   # detect
   - [[35, 38, 41], 1, Detect, [nc]]  # Detect(P3, P4, P5)

{ultralytics-8.1.42 → ultralytics-8.1.44}/ultralytics/data/__init__.py

@@ -1,19 +1,14 @@
 # Ultralytics YOLO 🚀, AGPL-3.0 license
 
 from .base import BaseDataset
-from .build import (
-    build_dataloader,
-    build_yolo_dataset,
-    build_grounding,
-    load_inference_source,
-)
+from .build import build_dataloader, build_grounding, build_yolo_dataset, load_inference_source
 from .dataset import (
     ClassificationDataset,
+    GroundingDataset,
     SemanticDataset,
+    YOLOConcatDataset,
     YOLODataset,
     YOLOMultiModalDataset,
-    GroundingDataset,
-    YOLOConcatDataset,
 )
 
 __all__ = (

{ultralytics-8.1.42 → ultralytics-8.1.44}/ultralytics/data/augment.py

@@ -8,7 +8,7 @@ from typing import Tuple, Union
 import cv2
 import numpy as np
 import torch
-import torchvision.transforms as T
+from PIL import Image
 
 from ultralytics.utils import LOGGER, colorstr
 from ultralytics.utils.checks import check_version
@@ -20,7 +20,7 @@ from .utils import polygons2masks, polygons2masks_overlap
 
 DEFAULT_MEAN = (0.0, 0.0, 0.0)
 DEFAULT_STD = (1.0, 1.0, 1.0)
-DEFAULT_CROP_FTACTION = 1.0
+DEFAULT_CROP_FRACTION = 1.0
 
 
 # TODO: we might need a BaseTransform to make all these augments be compatible with both classification and semantic
@@ -167,8 +167,8 @@ class BaseMixTransform:
         text2id = {text: i for i, text in enumerate(mix_texts)}
 
         for label in [labels] + labels["mix_labels"]:
-            for i, l in enumerate(label["cls"].squeeze(-1).tolist()):
-                text = label["texts"][int(l)]
+            for i, cls in enumerate(label["cls"].squeeze(-1).tolist()):
+                text = label["texts"][int(cls)]
                 label["cls"][i] = text2id[tuple(text)]
             label["texts"] = mix_texts
         return labels
@@ -1133,8 +1133,8 @@ def classify_transforms(
     size=224,
     mean=DEFAULT_MEAN,
     std=DEFAULT_STD,
-    interpolation: T.InterpolationMode = T.InterpolationMode.BILINEAR,
-    crop_fraction: float = DEFAULT_CROP_FTACTION,
+    interpolation=Image.BILINEAR,
+    crop_fraction: float = DEFAULT_CROP_FRACTION,
 ):
     """
     Classification transforms for evaluation/inference. Inspired by timm/data/transforms_factory.py.
@@ -1149,6 +1149,7 @@ def classify_transforms(
     Returns:
         (T.Compose): torchvision transforms
     """
+    import torchvision.transforms as T  # scope for faster 'import ultralytics'
 
     if isinstance(size, (tuple, list)):
         assert len(size) == 2
@@ -1157,12 +1158,12 @@ def classify_transforms(
         scale_size = math.floor(size / crop_fraction)
         scale_size = (scale_size, scale_size)
 
-    # aspect ratio is preserved, crops center within image, no borders are added, image is lost
+    # Aspect ratio is preserved, crops center within image, no borders are added, image is lost
     if scale_size[0] == scale_size[1]:
-        # simple case, use torchvision built-in Resize w/ shortest edge mode (scalar size arg)
+        # Simple case, use torchvision built-in Resize with the shortest edge mode (scalar size arg)
         tfl = [T.Resize(scale_size[0], interpolation=interpolation)]
     else:
-        # resize shortest edge to matching target dim for non-square target
+        # Resize the shortest edge to matching target dim for non-square target
         tfl = [T.Resize(scale_size)]
     tfl += [T.CenterCrop(size)]
 
@@ -1192,7 +1193,7 @@ def classify_augmentations(
     hsv_v=0.4,  # image HSV-Value augmentation (fraction)
     force_color_jitter=False,
     erasing=0.0,
-    interpolation: T.InterpolationMode = T.InterpolationMode.BILINEAR,
+    interpolation=Image.BILINEAR,
 ):
     """
     Classification transforms with augmentation for training. Inspired by timm/data/transforms_factory.py.
@@ -1216,7 +1217,9 @@ def classify_augmentations(
     Returns:
         (T.Compose): torchvision transforms
     """
-    # Transforms to apply if albumentations not installed
+    # Transforms to apply if Albumentations not installed
+    import torchvision.transforms as T  # scope for faster 'import ultralytics'
+
     if not isinstance(size, int):
         raise TypeError(f"classify_transforms() size {size} must be integer, not (list, tuple)")
     scale = tuple(scale or (0.08, 1.0))  # default imagenet scale range

{ultralytics-8.1.42 → ultralytics-8.1.44}/ultralytics/data/base.py

@@ -15,7 +15,7 @@ import psutil
 from torch.utils.data import Dataset
 
 from ultralytics.utils import DEFAULT_CFG, LOCAL_RANK, LOGGER, NUM_THREADS, TQDM
-from .utils import HELP_URL, FORMATS_HELP_MSG, IMG_FORMATS
+from .utils import FORMATS_HELP_MSG, HELP_URL, IMG_FORMATS
 
 
 class BaseDataset(Dataset):

{ultralytics-8.1.42 → ultralytics-8.1.44}/ultralytics/data/build.py

@@ -22,7 +22,7 @@ from ultralytics.data.loaders import (
 from ultralytics.data.utils import IMG_FORMATS, VID_FORMATS
 from ultralytics.utils import RANK, colorstr
 from ultralytics.utils.checks import check_file
-from .dataset import YOLODataset, YOLOMultiModalDataset, GroundingDataset
+from .dataset import GroundingDataset, YOLODataset, YOLOMultiModalDataset
 from .utils import PIN_MEMORY
 
 

{ultralytics-8.1.42 → ultralytics-8.1.44}/ultralytics/data/converter.py

@@ -519,11 +519,12 @@ def yolo_bbox2segment(im_dir, save_dir=None, sam_model="sam_b.pt"):
                 ├─ ..
                 └─ NNN.txt
     """
+    from tqdm import tqdm
+
+    from ultralytics import SAM
     from ultralytics.data import YOLODataset
-    from ultralytics.utils.ops import xywh2xyxy
     from ultralytics.utils import LOGGER
-    from ultralytics import SAM
-    from tqdm import tqdm
+    from ultralytics.utils.ops import xywh2xyxy
 
     # NOTE: add placeholder to pass class index check
     dataset = YOLODataset(im_dir, data=dict(names=list(range(1000))))